Using generative artificial intelligence to evaluate fine-tuned language models.
U.S. Patent No. 18/485,204. Washington, DC: U.S. Patent and Trademark Office., 2024
Recommended citation: Victor S. Bursztyn, Xiang Chen, Vaishnavi MUPPALA, Uttaran BHATTACHARYA, Tong Yu, Saayan Mitra, Ryan Rossi, Manas Garg, Kenneth George RUSSELL, Eunyee Koh, Alexandru Ionut Hodorogea. 2025. Using generative artificial intelligence to evaluate fine-tuned language models. U.S. Patent No. 18/485,204. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US20250124235A1/en
Methods and systems are provided for using generative artificial intelligence to evaluate fine-tuned language models. In embodiments described herein, natural language text snippets are generated via a generative language model based on corresponding data. A language model is fine-tuned into a fine-tuned language model via a language model fine-tuning component using the natural language text snippets and the corresponding data as training data. Independent natural language text snippets are generated via the generative language model based on the corresponding data. Each independent natural language text snippet is different than each corresponding natural language text snippet. An evaluation metric of the fine-tuned language model is generated via an evaluation component based on the independent natural language text snippets and the corresponding data.